|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4989338219165802, |
|
"min": 0.4989338219165802, |
|
"max": 1.4467018842697144, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 15039.861328125, |
|
"min": 15039.861328125, |
|
"max": 43887.1484375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989952.0, |
|
"min": 29952.0, |
|
"max": 989952.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989952.0, |
|
"min": 29952.0, |
|
"max": 989952.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.2658349871635437, |
|
"min": -0.10053335875272751, |
|
"max": 0.3569561541080475, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 67.78791809082031, |
|
"min": -24.128005981445312, |
|
"max": 95.30729675292969, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.08817770332098007, |
|
"min": -0.08869624882936478, |
|
"max": 0.24589866399765015, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 22.485313415527344, |
|
"min": -23.23841667175293, |
|
"max": 59.26157760620117, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06725213834267509, |
|
"min": 0.06540953831865219, |
|
"max": 0.07280490100850072, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9415299367974512, |
|
"min": 0.49919389069097747, |
|
"max": 1.0637078605781713, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01486007279059517, |
|
"min": 0.00015196046157249057, |
|
"max": 0.018790925071186373, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.20804101906833236, |
|
"min": 0.0019754860004423773, |
|
"max": 0.2630729509966092, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.67943315450714e-06, |
|
"min": 7.67943315450714e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010751206416309996, |
|
"min": 0.00010751206416309996, |
|
"max": 0.0033766606744464996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10255977857142859, |
|
"min": 0.10255977857142859, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4358369000000002, |
|
"min": 1.3886848, |
|
"max": 2.4255535000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002657218792857142, |
|
"min": 0.0002657218792857142, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0037201063099999987, |
|
"min": 0.0037201063099999987, |
|
"max": 0.11257279465, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010349963791668415, |
|
"min": 0.010349963791668415, |
|
"max": 0.43760281801223755, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14489948749542236, |
|
"min": 0.14489948749542236, |
|
"max": 3.0632197856903076, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 539.4705882352941, |
|
"min": 450.94029850746267, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 27513.0, |
|
"min": 15984.0, |
|
"max": 32661.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.0682352614753388, |
|
"min": -1.0000000521540642, |
|
"max": 1.399758175571463, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 54.47999833524227, |
|
"min": -31.998001664876938, |
|
"max": 93.78379776328802, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.0682352614753388, |
|
"min": -1.0000000521540642, |
|
"max": 1.399758175571463, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 54.47999833524227, |
|
"min": -31.998001664876938, |
|
"max": 93.78379776328802, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.057635682237827605, |
|
"min": 0.051854484241956204, |
|
"max": 8.997775060124695, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.9394197941292077, |
|
"min": 2.9394197941292077, |
|
"max": 143.96440096199512, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1690620334", |
|
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1690622643" |
|
}, |
|
"total": 2309.5441701190002, |
|
"count": 1, |
|
"self": 0.7757731510000667, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.033396288999938406, |
|
"count": 1, |
|
"self": 0.033396288999938406 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2308.735000679, |
|
"count": 1, |
|
"self": 1.7205963049950697, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.053613778999988, |
|
"count": 1, |
|
"self": 4.053613778999988 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2302.8535747910055, |
|
"count": 63448, |
|
"self": 1.6485339271152952, |
|
"children": { |
|
"env_step": { |
|
"total": 1595.8768007419712, |
|
"count": 63448, |
|
"self": 1467.422171605083, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 127.46433837696077, |
|
"count": 63448, |
|
"self": 5.486844123051924, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 121.97749425390884, |
|
"count": 62575, |
|
"self": 121.97749425390884 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.990290759927575, |
|
"count": 63448, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2302.8681246190304, |
|
"count": 63448, |
|
"is_parallel": true, |
|
"self": 968.4162673719607, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002555375999691023, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007806479989085346, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0017747280007824884, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0017747280007824884 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05374224899969704, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006642640000791289, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005654800002048432, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005654800002048432 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05033247899973503, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05033247899973503 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.002180025999678037, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000466957999378792, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0017130680002992449, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0017130680002992449 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1334.4518572470697, |
|
"count": 63447, |
|
"is_parallel": true, |
|
"self": 37.269566766028674, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 26.194841395091316, |
|
"count": 63447, |
|
"is_parallel": true, |
|
"self": 26.194841395091316 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1153.692229456954, |
|
"count": 63447, |
|
"is_parallel": true, |
|
"self": 1153.692229456954 |
|
}, |
|
"steps_from_proto": { |
|
"total": 117.29521962899571, |
|
"count": 63447, |
|
"is_parallel": true, |
|
"self": 24.519065462900016, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 92.7761541660957, |
|
"count": 507576, |
|
"is_parallel": true, |
|
"self": 92.7761541660957 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 705.328240121919, |
|
"count": 63448, |
|
"self": 2.985093205888461, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 123.81422134503282, |
|
"count": 63448, |
|
"self": 123.5287228040329, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.28549854099992444, |
|
"count": 2, |
|
"self": 0.28549854099992444 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 578.5289255709977, |
|
"count": 447, |
|
"self": 380.21240735703896, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 198.31651821395872, |
|
"count": 22806, |
|
"self": 198.31651821395872 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0699995982577093e-06, |
|
"count": 1, |
|
"self": 1.0699995982577093e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10721473400008108, |
|
"count": 1, |
|
"self": 0.001527168999928108, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10568756500015297, |
|
"count": 1, |
|
"self": 0.10568756500015297 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |